def test_different_table_rows(self):
"""
Test tables that are otherwise identical but one has more rows than the
other.
"""
ca1 = Column('A', format='L', array=[True, False])
cb1 = Column('B', format='L', array=[True, False])
ca2 = Column('A', format='L', array=[True, False, True])
cb2 = Column('B', format='L', array=[True, False, True])
ta = BinTableHDU.from_columns([ca1, cb1])
tb = BinTableHDU.from_columns([ca2, cb2])
diff = TableDataDiff(ta.data, tb.data)
assert not diff.identical
assert diff.diff_column_count == ()
assert len(diff.common_columns) == 2
assert diff.diff_rows == (2, 3)
assert diff.diff_values == []
report = diff.report()
assert 'Table rows differ' in report
assert 'a: 2' in report
assert 'b: 3' in report
assert 'No further data comparison performed.'
def test_different_table_field_counts(self):
"""
Test tables with some common columns, but different number of columns
overall.
"""
ca = Column('A', format='L', array=[True, False])
cb = Column('B', format='L', array=[True, False])
cc = Column('C', format='L', array=[True, False])
ta = BinTableHDU.from_columns([cb])
tb = BinTableHDU.from_columns([ca, cb, cc])
diff = TableDataDiff(ta.data, tb.data)
assert not diff.identical
assert diff.diff_column_count == (1, 3)
assert len(diff.common_columns) == 1
assert diff.common_column_names == {'b'}
assert diff.diff_column_names == ([], ['A', 'C'])
assert diff.diff_ratio == 0
assert diff.diff_total == 0
report = diff.report()
assert ' Tables have different number of columns:' in report
assert ' a: 1\n b: 3' in report
def test_ignore_table_fields(self):
c1 = Column('A', format='L', array=[True, False])
c2 = Column('B', format='X', array=[[0], [1]])
c3 = Column('C',
format='4I',
dim='(2, 2)',
array=[[0, 1, 2, 3], [4, 5, 6, 7]])
c4 = Column('B', format='X', array=[[1], [0]])
c5 = Column('C',
format='4I',
dim='(2, 2)',
array=[[1, 2, 3, 4], [5, 6, 7, 8]])
ta = BinTableHDU.from_columns([c1, c2, c3])
tb = BinTableHDU.from_columns([c1, c4, c5])
diff = TableDataDiff(ta.data, tb.data, ignore_fields=['B', 'C'])
assert diff.identical
# The only common column should be c1
assert len(diff.common_columns) == 1
assert diff.common_column_names == {'a'}
assert diff.diff_ratio == 0
assert diff.diff_total == 0
def test_identical_tables(self):
c1 = Column('A', format='L', array=[True, False])
c2 = Column('B', format='X', array=[[0], [1]])
c3 = Column('C',
format='4I',
dim='(2, 2)',
array=[[0, 1, 2, 3], [4, 5, 6, 7]])
c4 = Column('D', format='J', bscale=2.0, array=[0, 1])
c5 = Column('E', format='A3', array=['abc', 'def'])
c6 = Column('F', format='E', unit='m', array=[0.0, 1.0])
c7 = Column('G', format='D', bzero=-0.1, array=[0.0, 1.0])
c8 = Column('H', format='C', array=[0.0 + 1.0j, 2.0 + 3.0j])
c9 = Column('I', format='M', array=[4.0 + 5.0j, 6.0 + 7.0j])
c10 = Column('J', format='PI(2)', array=[[0, 1], [2, 3]])
columns = [c1, c2, c3, c4, c5, c6, c7, c8, c9, c10]
ta = BinTableHDU.from_columns(columns)
tb = BinTableHDU.from_columns([c.copy() for c in columns])
diff = TableDataDiff(ta.data, tb.data)
assert diff.identical
assert len(diff.common_columns) == 10
assert diff.common_column_names == set('abcdefghij')
assert diff.diff_ratio == 0
assert diff.diff_total == 0
def test_diff_empty_tables(self):
"""
Regression test for https://aeon.stsci.edu/ssb/trac/pyfits/ticket/178
Ensure that diffing tables containing empty data doesn't crash.
"""
c1 = Column('D', format='J')
c2 = Column('E', format='J')
thdu = BinTableHDU.from_columns([c1, c2], nrows=0)
hdula = fits.HDUList([thdu])
hdulb = fits.HDUList([thdu])
diff = FITSDiff(hdula, hdulb)
assert diff.identical
def test_different_table_field_names(self):
ca = Column('A', format='L', array=[True, False])
cb = Column('B', format='L', array=[True, False])
cc = Column('C', format='L', array=[True, False])
ta = BinTableHDU.from_columns([ca, cb])
tb = BinTableHDU.from_columns([ca, cc])
diff = TableDataDiff(ta.data, tb.data)
assert not diff.identical
assert len(diff.common_columns) == 1
assert diff.common_column_names == {'a'}
assert diff.diff_column_names == (['B'], ['C'])
assert diff.diff_ratio == 0
assert diff.diff_total == 0
report = diff.report()
assert 'Extra column B of format L in a' in report
assert 'Extra column C of format L in b' in report
def columns(self):
if self._has_data and hasattr(self.data, '_coldefs'):
return self.data._coldefs
format = self._bitpix2tform[self._header['BITPIX']]
pcount = self._header['PCOUNT']
parnames = []
bscales = []
bzeros = []
for idx in range(pcount):
bscales.append(self._header.get('PSCAL' + str(idx + 1), None))
bzeros.append(self._header.get('PZERO' + str(idx + 1), None))
parnames.append(self._header['PTYPE' + str(idx + 1)])
formats = [format] * len(parnames)
dim = [None] * len(parnames)
# Now create columns from collected parameters, but first add the DATA
# column too, to contain the group data.
parnames.append('DATA')
bscales.append(self._header.get('BSCALE'))
bzeros.append(self._header.get('BZEROS'))
data_shape = self.shape[:-1]
formats.append(str(int(np.prod(data_shape))) + format)
dim.append(data_shape)
parnames = _unique_parnames(parnames)
self._data_field = parnames[-1]
cols = [
Column(name=name, format=fmt, bscale=bscale, bzero=bzero,
dim=dim) for name, fmt, bscale, bzero, dim in zip(
parnames, formats, bscales, bzeros, dim)
]
coldefs = ColDefs(cols)
return coldefs
def __new__(cls, input=None, bitpix=None, pardata=None, parnames=[],
bscale=None, bzero=None, parbscales=None, parbzeros=None):
"""
Parameters
----------
input : array or FITS_rec instance
input data, either the group data itself (a
`numpy.ndarray`) or a record array (`FITS_rec`) which will
contain both group parameter info and the data. The rest
of the arguments are used only for the first case.
bitpix : int
data type as expressed in FITS ``BITPIX`` value (8, 16, 32,
64, -32, or -64)
pardata : sequence of arrays
parameter data, as a list of (numeric) arrays.
parnames : sequence of str
list of parameter names.
bscale : int
``BSCALE`` of the data
bzero : int
``BZERO`` of the data
parbscales : sequence of int
list of bscales for the parameters
parbzeros : sequence of int
list of bzeros for the parameters
"""
if not isinstance(input, FITS_rec):
if pardata is None:
npars = 0
else:
npars = len(pardata)
if parbscales is None:
parbscales = [None] * npars
if parbzeros is None:
parbzeros = [None] * npars
if parnames is None:
parnames = ['PAR{}'.format(idx + 1) for idx in range(npars)]
if len(parnames) != npars:
raise ValueError('The number of parameter data arrays does '
'not match the number of parameters.')
unique_parnames = _unique_parnames(parnames + ['DATA'])
if bitpix is None:
bitpix = DTYPE2BITPIX[input.dtype.name]
fits_fmt = GroupsHDU._bitpix2tform[bitpix] # -32 -> 'E'
format = FITS2NUMPY[fits_fmt] # 'E' -> 'f4'
data_fmt = '{}{}'.format(str(input.shape[1:]), format)
formats = ','.join(([format] * npars) + [data_fmt])
gcount = input.shape[0]
cols = [Column(name=unique_parnames[idx], format=fits_fmt,
bscale=parbscales[idx], bzero=parbzeros[idx])
for idx in range(npars)]
cols.append(Column(name=unique_parnames[-1], format=fits_fmt,
bscale=bscale, bzero=bzero))
coldefs = ColDefs(cols)
self = FITS_rec.__new__(cls,
np.rec.array(None,
formats=formats,
names=coldefs.names,
shape=gcount))
# By default the data field will just be 'DATA', but it may be
# uniquified if 'DATA' is already used by one of the group names
self._data_field = unique_parnames[-1]
self._coldefs = coldefs
self.parnames = parnames
for idx, name in enumerate(unique_parnames[:-1]):
column = coldefs[idx]
# Note: _get_scale_factors is used here and in other cases
# below to determine whether the column has non-default
# scale/zero factors.
# TODO: Find a better way to do this than using this interface
scale, zero = self._get_scale_factors(column)[3:5]
if scale or zero:
self._cache_field(name, pardata[idx])
else:
np.rec.recarray.field(self, idx)[:] = pardata[idx]
column = coldefs[self._data_field]
scale, zero = self._get_scale_factors(column)[3:5]
if scale or zero:
self._cache_field(self._data_field, input)
else:
np.rec.recarray.field(self, npars)[:] = input
else:
self = FITS_rec.__new__(cls, input)
self.parnames = None
return self
def test_different_table_data(self):
"""
Test diffing table data on columns of several different data formats
and dimensions.
"""
ca1 = Column('A', format='L', array=[True, False])
ca2 = Column('B', format='X', array=[[0], [1]])
ca3 = Column('C',
format='4I',
dim='(2, 2)',
array=[[0, 1, 2, 3], [4, 5, 6, 7]])
ca4 = Column('D', format='J', bscale=2.0, array=[0.0, 2.0])
ca5 = Column('E', format='A3', array=['abc', 'def'])
ca6 = Column('F', format='E', unit='m', array=[0.0, 1.0])
ca7 = Column('G', format='D', bzero=-0.1, array=[0.0, 1.0])
ca8 = Column('H', format='C', array=[0.0 + 1.0j, 2.0 + 3.0j])
ca9 = Column('I', format='M', array=[4.0 + 5.0j, 6.0 + 7.0j])
ca10 = Column('J', format='PI(2)', array=[[0, 1], [2, 3]])
cb1 = Column('A', format='L', array=[False, False])
cb2 = Column('B', format='X', array=[[0], [0]])
cb3 = Column('C',
format='4I',
dim='(2, 2)',
array=[[0, 1, 2, 3], [5, 6, 7, 8]])
cb4 = Column('D', format='J', bscale=2.0, array=[2.0, 2.0])
cb5 = Column('E', format='A3', array=['abc', 'ghi'])
cb6 = Column('F', format='E', unit='m', array=[1.0, 2.0])
cb7 = Column('G', format='D', bzero=-0.1, array=[2.0, 3.0])
cb8 = Column('H', format='C', array=[1.0 + 1.0j, 2.0 + 3.0j])
cb9 = Column('I', format='M', array=[5.0 + 5.0j, 6.0 + 7.0j])
cb10 = Column('J', format='PI(2)', array=[[1, 2], [3, 4]])
ta = BinTableHDU.from_columns(
[ca1, ca2, ca3, ca4, ca5, ca6, ca7, ca8, ca9, ca10])
tb = BinTableHDU.from_columns(
[cb1, cb2, cb3, cb4, cb5, cb6, cb7, cb8, cb9, cb10])
diff = TableDataDiff(ta.data, tb.data, numdiffs=20)
assert not diff.identical
# The column definitions are the same, but not the column values
assert diff.diff_columns == ()
assert diff.diff_values[0] == (('A', 0), (True, False))
assert diff.diff_values[1] == (('B', 1), ([1], [0]))
assert diff.diff_values[2][0] == ('C', 1)
assert (diff.diff_values[2][1][0] == [[4, 5], [6, 7]]).all()
assert (diff.diff_values[2][1][1] == [[5, 6], [7, 8]]).all()
assert diff.diff_values[3] == (('D', 0), (0, 2.0))
assert diff.diff_values[4] == (('E', 1), ('def', 'ghi'))
assert diff.diff_values[5] == (('F', 0), (0.0, 1.0))
assert diff.diff_values[6] == (('F', 1), (1.0, 2.0))
assert diff.diff_values[7] == (('G', 0), (0.0, 2.0))
assert diff.diff_values[8] == (('G', 1), (1.0, 3.0))
assert diff.diff_values[9] == (('H', 0), (0.0 + 1.0j, 1.0 + 1.0j))
assert diff.diff_values[10] == (('I', 0), (4.0 + 5.0j, 5.0 + 5.0j))
assert diff.diff_values[11][0] == ('J', 0)
assert (diff.diff_values[11][1][0] == [0, 1]).all()
assert (diff.diff_values[11][1][1] == [1, 2]).all()
assert diff.diff_values[12][0] == ('J', 1)
assert (diff.diff_values[12][1][0] == [2, 3]).all()
assert (diff.diff_values[12][1][1] == [3, 4]).all()
assert diff.diff_total == 13
assert diff.diff_ratio == 0.65
report = diff.report()
assert ('Column A data differs in row 0:\n'
' a> True\n'
' b> False') in report
assert ('...and at 1 more indices.\n'
' Column D data differs in row 0:') in report
assert ('13 different table data element(s) found (65.00% different)'
in report)
assert report.count('more indices') == 1